Buwei He's picture

47 3 1

Buwei He

Hermi2023

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

upvoted a paper 7 months ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

upvoted a paper 9 months ago

From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens

View all activity

Organizations

None yet

models 13

Hermi2023/doc2query-ppo-msmarco-128-12000

Updated Aug 6, 2023 • 3

Hermi2023/doc2query-ppo-msmarco-32-512

Updated Aug 6, 2023 • 13

Hermi2023/doc2query-ppo-msmarco-128-4096

Updated Aug 6, 2023 • 12

Hermi2023/doc2query-ppo-msmarco-128-2048

Updated Aug 6, 2023 • 7

Hermi2023/doc2query-ppo-msmarco-128-1024

Updated Aug 6, 2023 • 9

Hermi2023/doc2query-ppo-msmarco-batch-256-doc-43520-mono

Updated Aug 4, 2023 • 21

Hermi2023/doc2query-ppo-msmarco-43520-121

Reinforcement Learning • Updated Aug 4, 2023 • 11

Hermi2023/doc2query-ppo-msmarco-12000-mini-121

Updated Aug 4, 2023 • 7

Hermi2023/doc2query-ppo-msmarco-batch-256-doc-43520-duo

Updated Aug 4, 2023 • 6

Hermi2023/doc2query-ppo-msmarco-8192-mini-121

Updated Aug 1, 2023 • 10

datasets 0

None public yet